© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129354
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rattled
    -0.07
    Browse
    -0.06
     తీవ్ర
    -0.06
    Conversely
    -0.06
    svp
    -0.06
    onic
    -0.06
     جلوگیری
    -0.06
     grim
    -0.06
     ನೆಲ
    -0.06
     pestaña
    -0.06
    POSITIVE LOGITS
     so
    0.07
     amphibious
    0.06
    なので
    0.06
     don
    0.06
     tropical
    0.06
    那么
    0.05
     identificación
    0.05
     identific
    0.05
    Unmarshal
    0.05
    同时
    0.05
    Activations Density 0.000%

    No Known Activations